[1]HUANG Jian-hua,TANG Xiang-long,LIU Jia-feng,et al.A new method for text detection based on Homogeneity[J].CAAI Transactions on Intelligent Systems,2007,2(1):69-73.
Copy

A new method for text detection based on Homogeneity

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 2 Number of periods: 2007 1 Page number: 69-73 Column: 学术论文—自然语言处理与理解 Public date: 2007-02-25
Title:
A new method for text detection based on Homogeneity
Author(s):
HUANG Jian-hua; TANG Xiang-long; LIU Jia-feng; XU Li-li
School of Computer Science and Technology, Harbin Institute of Technology, Harbi n 150001, China
Keywords:
text detection; feature extraction; Homogeneity; SVM
CLC:
TP391.2
DOI:
-
Abstract:
Text data presented in images and video contains useful and important semantic information for automatic indexing. In this paper, a method for text d etection based on homogeneity and SVM is proposed. First an original image is m apped from space domain to homogeneity domain, and then text region property is conf irmed by SVM trained to extract property feature in homogeneity domain. Comparis on with the text detection method based on edge features shows that the proposed method has a better accuracy.
References:
［1］ JEONG K Y, JUNG K, KIM E Y, et al： Neural networkbased text location f or news video indexing［J］. IEEE Transactions on Information Theory, 1998, 44(5): 319-323.
［2］KIM K I, JUNG K, KIM J H. Texturebased approach for text detection in i ma ges using support vector machines and continuously adaptive mean shift algorithm ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003, 25(1 2):1631-1639.
［3］LI H P, DOERMANN D, KIA O. Automatic text detection and tracking in digi tal video［J］. IEEE Transaction on Image Processing, 2000, 9(1):147-156.
［4］CHEN X R, ZHANG H J. Text area detection from video frames［A］. IEEE Pa cifi c Rim Conference on Multimedia: Advances in Multimedia Information Processing［C ］.［s.l.］,2001.
［5］LIENHART R, WERNICKE A. Localizing and segmentation text in images a nd videos［J］. IEEE Transactions On Circuits and Systems For Video Technology, 2000, 12(4):256-268.
［6］YE Q X, HUANG Q M, GAO W, ZHAO D B. Fast and robust text detection in images and video frames［J］. Image Vision and Computing, 2005(23):565-576. 
［7］张 引,潘云鹤.面向彩色图像和视频的文本提取新方法［J］. 计算机辅助设计与图形学报，2002, 14(1):36-40.
ZHANG Yin, PAN Yunhe. A new approach for text extraction from color image and vi deo［J］. Journal of Computeraided Design & Computer Graphics,2002, 14(1): 36- 40.
［8］ZHONG Y, ZHANG Hongjiang, JAIN A K. Automatic caption location in co mpressed video［J］. IEEE Transactions on Pattern Analysis and Machine Intellige nce,2000, 22(4):385-392
［9］LUCAS S M, PANARETOS A, SOSA L. ICDAR 2003 robust reading competitio n［A］. In: IEEE Proceeding of The 7th International Conference on Document Anal ysis and Recognition［C］.［s.l.］,2003.
Similar References:

Memo

-

Last Update: 2009-05-05

Copyright © CAAI Transactions on Intelligent Systems